New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

Pixi Inspector

Unverified
NPMpixi-inspector-mcp
FRisk gradecritical blast radius
Catalogue entry updated 10 days ago
Auth postureNot probedno remote endpoint probed yet
Tools6311 Destructive · 3 Execute · 3 Write · 6 Read · 40 Other
Worst categoryDestructivegrade tracks the peak, not the average
Capability mix
Destructive 11Execute 3Write 3Read 6Other 40
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Exfiltration pathReads content an attacker can plant and can send data outward — a prompt-injection-to-exfiltration route.
Tools 63
cdp.console.startDestructiveHighcdp.emulate.cpuDestructiveHighcdp.emulate.deviceDestructiveHighcdp.emulate.networkDestructiveHighcdp.emulate.touchDestructiveHigh
View all 63 tools
These definitions cost 19,694 tokens of context →
Change history
No change history on record for this server.
Recommended policy
cdp.console.startdeny
cdp.console.listrequire approval
cdp.performance.trace.stoprate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

This record as markdown: /tools/pixi-inspector-mcp.md — append .md to any tool or server page.

DIRECT INSTALL npx -y pixi-inspector-mcp

Installed this way, nothing enforces the recommended policy above — calls run exactly as the agent makes them.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.